The following products share capabilities with Document AI. However, these products perform a specific text and analysis function. Depending on your use case, these products might provide the specific capabilities you need.
Convert images to text
You can convert content in images to text using either:
- Enterprise Document OCR.
Cloud Vision API (using the
TEXT_DETECTIONorDOCUMENT_TEXT_DETECTIONenums). See:
Detect visual artifacts
You can use AutoML Vision object detection to convert sections of images into text documents. For details, see Image data.
Classify documents
With document plain text and running OCR beforehand, you can categorize and label documents using the following products:
- The pretrained Natural Language API helps you classify content using a generalized list of categories.
- Use AutoML Natural Language classification to create a custom machine learning model, and classify content with your own category labels.
While there may be exceptions, AutoML Vision classification is not generally recommended for document classification because its tends to be less accurate than text-based methods. However, you can use it for classifying image content.
- This is not generally a recommended method for classification of documents, as its accuracy tends to be less than text based methods, but there may be exceptions
| Natural Language API | |
| AutoML Natural Language classification | |
| AutoML Vision classification |
Analyze and extract entities
You can identify known entities in documents (proper nouns such as public figures, company branding, and so on) and entities that follow common patterns such as phone numbers and addresses with using Form Parser or any of the pretrained processors for your use case.
- You can also use the Natural Language API to identify common, public entities.
- AutoML Natural Language products are for entity extraction. Use them to create a custom machine learning model to identify entities specific to your company or use case.
| Natural Language API | |
| AutoML Natural Language Entity Extraction |
Other products
- Vertex AI: Brings AutoML and AI Platform together into a unified API, client library, and platform.
- Cloud Translation API: Dynamically translates text between thousands of language pairs through pretrained models. Provides a document translation API for directly translating documents in formats such as PDF and DOCX. See Translate documents.
- Workflows: Combines Google Cloud services and APIs to build reliable applications, process automation, and data and machine learning pipelines.
- AppSheet Automation: Creates custom automations and applications with an open cloud.
- Stack by Area 120: The experimental Android app for categorizing and analyzing personal documents, powered by Document AI.
- Google Translate: This service instantly translates words, phrases, and web pages between English and over 100 other languages.
Find a partner
Take advantage of our growing partner ecosystem to help you create and manage your document analysis solution. For a list of partners and the services that they provide, see Document AI partners.